Clustering Algorithm for a Set of Machine Parts on the Basis of Engineering Drawings

Kuchuganov, Valeriy N.; Kuchuganov, Aleksandr V.; Kasimov, Denis R.

doi:10.1134/s0361768820010041

Cited by 5 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If it is lower than the end temperature, the algorithm ends and returns to the global optimal solution. If not, the temperature attenuation operation is cycled [22].…”

Section: Multiobjective Flexible Workhopmentioning

confidence: 99%

The Implementation of Multiobjective Flexible Workshop Scheduling Based on Genetic Simulated Annealing-Inspired Clustering Algorithm

Huang

Wang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Multiobjective flexible workshop scheduling is an important subject to improve resource utilization and production efficiency and enhance the competitiveness of enterprises. As the situation of resource constraints becomes more and more severe, the problem of companies rationally allocating limited resources in production is becoming more and more serious. Today, the manufacturing industry widely adopts advanced manufacturing modes such as computer-integrated manufacturing and intelligent manufacturing, but in these semi-intelligent manufacturing modes with a high degree of uncertainty and a high degree of personnel dependence, it is difficult to adapt to the work of large-scale production. Therefore, suitable clustering algorithms are urgently needed to help solve these problems, and this paper selects a clustering algorithm based on the genetic simulation annealing algorithm. This article is aimed at studying the problem of efficiency improvement in the production process of large-scale manufacturing and at finding a stronger and more effective production mode for the manufacturing industry. Firstly, this paper introduces the basic principles of simulated annealing genetic algorithm and regularized clustering algorithm. These algorithms have excellent performance in searching for global optimal solutions. They can be constantly tested and computed to keep the calculation results close to the global optimal solution. In this paper, the K -means clustering algorithm is used to select the shortest completion time to represent the clustering target. According to the minimum distance principle, the machine, workpiece, and other objects are input into the clustering of the algorithm, and the K -means algorithm will send out the sorting plan. Therefore, a multiobjective flexible job shop scheduling model based on genetic simulated annealing algorithm and clustering algorithm is established. Then, by using hypothetical production data to simulate the operation of the workshop, the scheduling model was applied to conduct a deduction and empirical comparative study. The experimental results showed that the model shortened the completion time of the workpiece by 4.4% and increased the average load rate of the machine by 10%.

show abstract

“…If it is lower than the end temperature, the algorithm ends and returns to the global optimal solution. If not, the temperature attenuation operation is cycled [22].…”

Section: Multiobjective Flexible Workhopmentioning

confidence: 99%